Instructions to use Letian2003/unified_vit_v96_100_128-vision-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use Letian2003/unified_vit_v96_100_128-vision-decoder with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:Letian2003/unified_vit_v96_100_128-vision-decoder') tokenizer = open_clip.get_tokenizer('hf-hub:Letian2003/unified_vit_v96_100_128-vision-decoder') - Notebooks
- Google Colab
- Kaggle
Upload standalone vision decoder: v96_100 stage-1 PRE (res128, 100ep, step 15639) reconstruction path
6b82e5a verified - Xet hash:
- 451351f993c26b1b54b21968a38b0fc41249832c48c6419460475566ff61f6ea
- Size of remote file:
- 154 MB
- SHA256:
- d9ab064543ecd6cc43edfb4fd022f89263d0576f8ab7c00d1fda2ef0acab5e18
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.